Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.8494. Min Act: -0.0000

Data Index: 991141 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.9255. Min Act: -0.0000

Data Index: 294283 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.6588. Min Act: -0.0000

Data Index: 583820 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.4271. Min Act: -0.0000

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.5322. Min Act: -0.0000

Data Index: 607055 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.6629. Min Act: -0.0000

Data Index: 420363 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.3736. Min Act: -0.0000

Data Index: 892240 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.6162. Min Act: -0.0000

Data Index: 1072080 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.3639. Min Act: -0.0000

Data Index: 210669 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.5508. Min Act: -0.0000

Data Index: 546014 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.5452. Min Act: -0.0000

Data Index: 210663 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.3812. Min Act: -0.0000

Data Index: 818218 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.2954. Min Act: -0.0000

Data Index: 313720 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.1673. Min Act: -0.0000

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.2835. Min Act: -0.0000

Data Index: 1267853 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.2719. Min Act: -0.0000

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.1457. Min Act: -0.0000

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.1870. Min Act: -0.0000

Data Index: 26550 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.1840. Min Act: -0.0000

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 2.9255. Min Range: -2.9255

Max Act: 2.1748. Min Act: -0.0000

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 681